http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112733614-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-462 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-60 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-25 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2413 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-60 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-25 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-82 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-46 |
filingDate | 2020-12-22-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2022-09-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2022-09-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-112733614-B |
titleOfInvention | A Pest Image Detection Method with Similar Size Enhanced Recognition |
abstract | The invention relates to a pest image detection method with enhanced identification of similar size, which solves the defect that it is difficult to detect pests of similar size in plant protection images compared with the prior art. The invention includes the following steps: acquiring a pest image data set and performing preprocessing; constructing a pest image detection network; training the pest image detection network; acquiring an image of a pest to be detected; and obtaining a pest image detection result. Through the self-learning weight and weighted attention feature pyramid, the present invention enables the convolutional neural network to focus on the feature layer corresponding to the size of most of the pest images in the data set, and improves the feature expression ability of the convolutional neural network to deal with similar The problem of misidentification of pests of different sizes; using the multi-scale anchor-free region proposal network, the subsequent classification and regression network can obtain better candidate regions, and realize the enhanced identification of pests of similar size, thereby improving the accuracy of pest identification and detection. |
priorityDate | 2020-12-22-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID451289241 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID23266 |
Total number of triples: 25.